© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42798
    Prev
    Next
    INDEX
    Explanations

    scripting languages VB and Basic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     கொண்டிருக்கும்
    0.62
    t
    0.61
    crime
    0.55
     Messe
    0.55
    पू
    0.53
    bear
    0.52
    crunch
    0.52
     Puebla
    0.52
    tae
    0.52
    yad
    0.51
    POSITIVE LOGITS
    셨
    0.59
     حسب
    0.51
     legitt
    0.49
    یتے
    0.47
     fût
    0.46
     contributo
    0.46
    șit
    0.46
     під
    0.45
     avevano
    0.45
    黾
    0.44
    Activations Density 0.048%

    No Known Activations